loop-briefing

loop-briefing is a skill for Claude Code, Codex from terrylica/cc-skills. It costs 154 tokens per session (644 once invoked), scanned A, original, MIT.

A notification tool for autonomous coding runs that sends a Pushover alert when a run is blocked and needs a decision, or when it has finished meaningful work. Pushover is a service that delivers alerts to devices.

In plain words
What is it for?
Use it with Claude Code loop runs to report a blocker such as a required authentication choice, or to announce that the work is complete. It can include the project, branch, status, recent commits, and supplied details.
Why use it?
It prevents a long-running coding task from waiting unnoticed for human input or ending without a clear notification. The alert includes project and Git context in a rendered incident image.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Part of the pushover-commander plugin — 9 skills shipped together , and of cc-skills

Good fit Use it with Claude Code loop runs to report a blocker such as a required authentication choice, or to announce that the work is complete. It can include the project, branch, status, recent commits, and supplied details.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/terrylica/cc-skills/loop-briefing
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add terrylica/cc-skills --skill loop-briefing
Clone the repo
git clone --depth 1 https://github.com/terrylica/cc-skills

Made for: Claude Code, Codex.

Or install pushover-commander, the plugin that ships this one along with the rest of its 9 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for loop-briefing

README.md
[![agentmods](https://agentmods.dev/badge/skills/terrylica/cc-skills/loop-briefing/github.svg)](https://agentmods.dev/skills/terrylica/cc-skills/loop-briefing)
Your own site
<a href="https://agentmods.dev/skills/terrylica/cc-skills/loop-briefing"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/loop-briefing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for loop-briefing

Your own site · 80×15
<a href="https://agentmods.dev/skills/terrylica/cc-skills/loop-briefing"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/loop-briefing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 644 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00154 $0.00644
Opus 5 $0.00077 $0.00322
Sonnet 5 $0.00031 $0.00129
Haiku 4.5 $0.00015 $0.00064

Measured 3d ago against content hash 16d378c14eba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

loop-briefing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/pushover-commander/skills/loop-briefing/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

loop-briefing

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

The original goal skill: a contextually-invoked briefing for autonomous /loop runs. Built on the TS core pushover_core.ts loop-brief, which gathers context (project, cwd, branch, git status, recent commits, plus any details you pass), renders it (Satori → PNG), and sends it (emergency+receipt for blocked, high-priority for done).

# BLOCKED — needs a decision now (emergency, alarms until you ack):
env -u HTTPS_PROXY -u HTTP_PROXY bun "$(cc-plugin-root pushover-commander)/skills/_lib/pushover_core.ts" loop-brief \
  --kind blocked --reason "must choose auth method" --body /tmp/decision_options.txt

# DONE — no meaningful work remains (high priority, no alarm):
env -u HTTPS_PROXY -u HTTP_PROXY bun "$(cc-plugin-root pushover-commander)/skills/_lib/pushover_core.ts" loop-brief \
  --kind done --reason "all tasks complete, matrix exhausted"

When to fire (the two-situation rule)

  1. Blocked — the loop cannot safely continue without a human: needs a decision, clarification, review, or a choice between options. Pair this with an AskUserQuestion call in the session so the options are presented in plain language with tradeoffs.
  2. Done — no meaningful remaining work under the initial or updated directives; the loop should stop scheduling further wakeups (CronDelete).

Do not fire for routine progress. The --body - form reads details from stdin.

Post-Execution Reflection

After this skill completes, check before closing:

  1. Did the block/done briefing fire at the right moment with the right git and session context? If it fired on routine progress or missed a real block, fix the trigger.
  2. Was the emergency vs high-priority routing correct? Blocked = emergency+receipt, done = high-priority — fix if swapped.

Read the full file on GitHub · 37 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 37 lines · 154 tokens per session scan A 16d378c14eba

Subscribe to this mod's changes

loop-briefing is a skill published in the GitHub repository terrylica/cc-skills (66 stars, last pushed today), licensed MIT. It adds 154 tokens to every session and 644 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other skills, from other repositories

session-status

Analyzes current session state without any cleanup. Full mode (default): resolves the active plan file, reads plan checklist + TaskList, gathers unfinished work/issues from conversation history, and emits a /handoff-built next-session prompt. Mid-session mode (/session-status mid): a fast plain-language 'done vs…

dryvist/claude-code-plugins · 102 tokens

ship

Commit, push, create PR(s), and auto-finalize — full automation pipeline. Handles uncommitted changes and recently created PRs.

dryvist/claude-code-plugins · 30 tokens

calendar

Google Calendar integration — check schedule, create events, daily briefings, proactive reminders. Triggers on "what's on my calendar", "add to calendar", "schedule a meeting", "when am I free", "daily briefing", or any calendar-related request.

k1p1l0/claude-telegram-supercharged · 55 tokens

native-first

Stack-agnostic discovery playbook for finding the native, non-custom way to do something before writing any script or wrapper. Use when tempted to write a shell/python/glue script, add a dependency, or build a custom helper — and whenever a script-guards hook blocks a script write. Climbs a fixed ladder (tool's own…

dryvist/claude-code-plugins · 117 tokens

configure

Set up the Telegram channel — save the bot token and review access policy. Use when the user pastes a Telegram bot token, asks to configure Telegram, asks "how do I set this up" or "who can reach me," or wants to check channel status.

k1p1l0/claude-telegram-supercharged · 56 tokens

cron-manager

Create, inspect, pause, and remove scheduled jobs using natural language descriptions.

profclaw/profclaw · 17 tokens